© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 868
    Prev
    Next
    INDEX
    Explanations

    browse

    np_max-act · gemini-2.0-flash

    This neuron activates on the names of the assistant’s built‐in commands (e.g., “Google Search,” “Browse Website,” “Start GPT Agent,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     임
    -0.06
     mest
    -0.06
    _DYNAMIC
    -0.06
     inclusion
    -0.06
    ิกายน
    -0.06
    .IsNullOr
    -0.06
     земля
    -0.06
    _TYPES
    -0.06
    _ACCEPT
    -0.06
     Snape
    -0.06
    POSITIVE LOGITS
    kening
    0.07
    /api
    0.07
    bew
    0.07
     v
    0.06
     countries
    0.06
     reigning
    0.06
    ACING
    0.06
     Atlantic
    0.06
     biking
    0.06
    诉
    0.06
    Activations Density 0.001%

    No Known Activations